The global advertising market is roughly US$1.1 trillion, before accounting for the wider investments firms make in pricing, promotions, loyalty, and customer acquisition. Yet the evidence used to measure these investments is often fragile. Traditional marketing mix models offer operational convenience, while modern econometric methods promise stronger causal identification. In practice, marketing teams must work with short panels, staggered rollouts, overlapping campaigns, platform interference, and competitive responses that make simple before-and-after comparisons unreliable.
 
Volume 1 of Causal Inference in Marketing: A Practical Toolkit for Panel Data develops the foundations and core panel designs needed to turn those messy data structures into credible causal evidence. Grounded in potential-outcomes reasoning and design-based thinking, it translates causal inference into the language of marketing measurement: incrementality, attribution, budget allocation, and decision-relevant reporting. The emphasis throughout is on clear estimands, credible identification, practical diagnostics, and recognising when the available data cannot support the causal claim being made.
 
Key Features:

• Provides a practitioner-first framework for causal panel design in marketing, including estimands, assignment mechanisms, support, diagnostics, and reporting standards.
• Covers the core modern panel toolkit, including difference-in-differences, staggered adoption designs, event studies, synthetic control, augmented synthetic control, synthetic difference-in-differences, interactive fixed effects, and matrix completion.
• Includes dedicated treatment of dynamic effects, heterogeneity, interference, and spillovers in advertising, pricing, loyalty, platforms, and marketing effectiveness settings.

 
Written for data scientists, marketing analysts, econometricians, and applied researchers, this volume is intended for readers who are comfortable with regression and applied statistics and want a rigorous, practical route from marketing panel data to causal evidence. Volume 2 extends the toolkit into machine learning, high-dimensional adjustment, continuous treatments, inference, diagnostics, applications, data systems, reproducibility, and future practice.
 
Charles Shaw is a Data Science Director at WPP Media, where he leads econometric measurement and optimisation for global brands. His work focuses on causal inference, econometric measurement, Bayesian modelling, machine learning, and marketing effectiveness. He develops applied frameworks for privacy-constrained attribution, media incrementality, platform effects, dynamic pricing, and scalable causal workflows in commercial settings.